maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
119,953 Commits 23 Branches 0 Tags 2.2 GiB
Commit Graph

42 Commits

Author SHA1 Message Date
Craig Topper 9f00948a82 Add AVX2 permute intrinsics. Also add parentheses on some macro arguments in other intrinsic headers. 
llvm-svn: 147241
 2011-12-24 07:55:14 +00:00
Bob Wilson c9b97cc1da Fix vector macros to correctly check argument types. <rdar://problem/10261670> 
llvm-svn: 143792
 2011-11-05 06:08:06 +00:00
Eli Friedman 9bb51adcce Tweak *mmintrin.h so that they don't make any bad assumptions about alignment (which probably has little effect in practice, but better to get it right). Make the load in _mm_loadh_pi and _mm_loadl_pi a single LLVM IR instruction to make optimizing easier for CodeGen. 
rdar://10054986

llvm-svn: 139874
 2011-09-15 23:15:27 +00:00
Bill Wendling 03e7e430c3 Add 'may_alias' attribute. Noticed by Eli. 
llvm-svn: 131278
 2011-05-13 01:24:00 +00:00
Bill Wendling 502931fad9 Represent the unaligned loads natively. These are converted into a call to the 
correct unaligned load.

llvm-svn: 131268
 2011-05-13 00:11:39 +00:00
Bill Wendling e106c34817 LLVM doesn't always optimize away the four loads from this: 
(__m128){ p[0], p[1], p[2], p[3] }

which produces really bad code. This could be done in instcombine, but it's
probably better to do it in the front-end instead.
<rdar://problem/9424836>

llvm-svn: 131237
 2011-05-12 19:02:15 +00:00
Bill Wendling 2c1c33552d Remove comment that snuck in there. 
llvm-svn: 129434
 2011-04-13 10:05:14 +00:00
Bill Wendling b9c9e34cb3 Just use a native "load" instead of translating the builtin later. Clang can 
take it!

I wasn't able to get __builtin_ia32_loaddqu to transform into an unaligned
load...I'll have to look into it further.

llvm-svn: 129427
 2011-04-13 05:58:17 +00:00
Chandler Carruth 45c2fb1e69 Undo part of my previous commit to mm_malloc.h, going back to the use of 
stdlib.h. There were numerous problems with forward declaring 'malloc' and
'free', but the most important is that these are reserved by POSIX and may be
implemented via a function-like macro.

As suggested by Dale Johannesen, I'm instead guarding the only include of this
in our builtin headers with __STDC_HOSTED__, and I've removed the include of
the header from the test suite. I'll discuss with folks whether we want to have
a hosted section of the test suite or not, and add it (and perhaps other tests)
back there if that's the direction.

llvm-svn: 119958
 2010-11-22 08:06:31 +00:00
Chris Lattner 07704f1d7e the mmx intrinsic for pshufw should map to the IR intrinsic, not 
to a shufflevector.  Otherwise it doesn't turn into a pshufw.
This bug was introduced in the mmx rewrite.

llvm-svn: 115423
 2010-10-02 21:32:59 +00:00
Chris Lattner 212a492063 fix incorrect MM_HINT_ definitions, PR8011 
llvm-svn: 112283
 2010-08-27 20:10:06 +00:00
Chandler Carruth 7579c008ec Fix some typos I made when adding alternate intrinsic names. 
llvm-svn: 110545
 2010-08-08 08:30:05 +00:00
Chandler Carruth 96f2e9e418 Add alternate names for x86 SIMD intrinsics. These aren't as common, but show 
up enough to be worth supporting properly. Fixes PR7674.

llvm-svn: 109086
 2010-07-22 06:47:28 +00:00
Daniel Dunbar f5e075d392 Headers: Fix quoting of macro arguments in a couple more places. 
llvm-svn: 105331
 2010-06-02 16:35:01 +00:00
Nick Lewycky 71eac6e114 Make macro safe in the face of users who pass "addr+64". Addition of void* is 
invalid.

llvm-svn: 105172
 2010-05-30 18:26:21 +00:00
Chris Lattner 6625c7028e add type casts to _mm_shuffle_ps so the front-end applies 
implicit conversions where needed.  This fixes an error reported
on cfe-dev, not really worth a testcase though.

llvm-svn: 103864
 2010-05-15 05:53:53 +00:00
Chris Lattner 7eac805bb0 fix PR6658: inline isn't a keyword in C89 mode, use __inline__ instead. 
llvm-svn: 99190
 2010-03-22 18:14:12 +00:00
Eric Christopher 33124e20c7 Migrate typedefs to the top level of xmmintrin.h and remove the same 
one from emmintrin.h.

llvm-svn: 99020
 2010-03-20 01:08:47 +00:00
Chris Lattner e983eae273 add two aliases for SSE functions we already have, fixing PR6316. 
llvm-svn: 96363
 2010-02-16 18:21:25 +00:00
Chris Lattner b18093e467 fix PR6187: various load functions in xmmintrin.h were missing 'const'. 
emmintrin looks ok.

llvm-svn: 94998
 2010-02-01 20:14:14 +00:00
Chris Lattner 0afd3a23cd fix a bug in the _MM_TRANSPOSE4_PS definition, patch by Brian Sumner from 
PR6138

llvm-svn: 94669
 2010-01-27 07:54:50 +00:00
Chris Lattner 4debb32fdd _mm_xor_ps does a xor not a nxor. The other 'xor' builtins look fine, 
but this one is wrong.  Thanks to Tanya for noticing this.

llvm-svn: 92881
 2010-01-07 00:36:41 +00:00
Eli Friedman 9d79bdaaad Following gcc, hide the hack to include the SSE2 intrinsics from 
xmmintrin.h in an ifdef.

llvm-svn: 73200
 2009-06-11 18:50:02 +00:00
Daniel Dunbar fcec758f4e xmmintrin needs to include emmintrin, Darwin system headers seem to depend on it 
defining m128[id], at least.

llvm-svn: 73021
 2009-06-07 08:33:23 +00:00
Eli Friedman 5a996fc0fc Now that LLVM CodeGen can handle the generic variations a bit better, 
get rid of a few more clang vector builtins.

llvm-svn: 73015
 2009-06-07 07:12:56 +00:00
Eli Friedman 4d8d7d3263 Replace more calls to builtins with generic code. 
llvm-svn: 72995
 2009-06-06 08:08:06 +00:00
Eli Friedman d00fd2885e Fix some casts to work without -flax-vector-conversions. 
llvm-svn: 72981
 2009-06-06 03:45:06 +00:00
Eli Friedman ebd9314f32 Misc fixes to MMX/SSE intrinsics: a few small bug fixes, and getting rid 
of calls to builtins for constructs which can be expressed directly.

llvm-svn: 72979
 2009-06-06 02:13:04 +00:00
Eli Friedman f83c258eae Add aliases for a couple of SSE intrinsics. Patch by Ed Schouten. 
llvm-svn: 72717
 2009-06-02 05:55:48 +00:00
Anders Carlsson 2081200b8c Add 'cmp' SSE builtins and get rid of a bunch of other builtins. 
llvm-svn: 72032
 2009-05-18 19:16:46 +00:00
Chris Lattner ff8a9e6ee4 fix misspelt attribute. 
llvm-svn: 69362
 2009-04-17 17:55:23 +00:00
Daniel Dunbar c9feeb54a5 Spell __always_inline__ correctly. 
llvm-svn: 64757
 2009-02-17 07:57:58 +00:00
Anders Carlsson 11352f9d63 Fix more xmmintrin.h typos 
llvm-svn: 64537
 2009-02-14 04:01:38 +00:00
Anders Carlsson 823c02eaab Add the nodebug attribute to intrinsics 
llvm-svn: 64519
 2009-02-14 01:00:11 +00:00
Mike Stump 5b31ed3ff0 80col. 
llvm-svn: 64450
 2009-02-13 14:24:50 +00:00
Anders Carlsson 5bc94e625b Fix some mistakes I made when I tried to decipher the Intel documentation of the MXCSR register 
llvm-svn: 64290
 2009-02-11 06:29:32 +00:00
Anders Carlsson 43c2bab6d3 Fix more bugs I discovered 
llvm-svn: 62656
 2009-01-21 01:49:39 +00:00
Anders Carlsson 7322ea25a5 Fix some errors I noticed 
llvm-svn: 62620
 2009-01-20 21:51:44 +00:00
Anders Carlsson f562b39e80 Add a MS specific intrinsic. 
llvm-svn: 61446
 2008-12-27 04:26:15 +00:00
Anders Carlsson 19ef5d49d4 OK, all tests pass. Let's start using the SSE2 header 
llvm-svn: 61440
 2008-12-26 00:57:11 +00:00
Anders Carlsson c72502308d Fix test failures noticed by Fariborz. 
llvm-svn: 61334
 2008-12-22 17:42:23 +00:00
Anders Carlsson e5f993da3d Flip the switch and start using the new xmmintrin.h 
llvm-svn: 61332
 2008-12-22 07:36:02 +00:00